eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Complete Phase 7 runner orchestration

Browse Source
This commit is contained in:
Eric Rakestraw
2026-05-11 14:22:22 +00:00
parent 30606f5c49
commit 28fe899aa1
8 changed files with 760 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
docs/architecture.md
View File

@@ -17,14 +17,15 @@ Implemented today:
- Per-run diagnostics directory creation plus Phase 6 process-level artifacts.
- Process report JSON output with diagnostics artifact references.
- Framework foundation packages for contracts and proposal application.
- Production runner orchestration package with deterministic sequential module execution.
- Module-level report structures with applied/skipped change records.
Not implemented in CLI runtime path today:
- Real module execution pipeline (`glossary`, `homophones`, `spoken_word`, `grammar`).
- Structured LLM proposal generation.
- Validator chain execution.
- Pipeline runner orchestration.
- Production LLM scheduler behavior.
- End-to-end transcript polishing beyond normalization.
- End-to-end transcript polishing with real module behavior.
## Actual Go package layout
@@ -73,6 +74,9 @@ internal/framework/proposals/
policy.go
preview.go
apply.go
internal/framework/runner/
runner.go
```
## Current CLI behavior
@@ -94,14 +98,15 @@ Current runtime flow (`internal/cli/run.go`):
9. Write normalized transcript and normalization summary artifacts.
10. Chunk normalized transcript and compute chunk summaries.
11. Write chunking summary artifact.
12. Output normalized transcript to `--output` file or stdout.
13. Build process report (`phase` currently set to `phase3-chunking`).
14. Optionally write `--report-json`; always write run-dir `report.json`.
15. Apply work-dir retention.
12. Optionally execute runner modules sequentially when an injected module registry/factory is available (used by deterministic tests today).
13. Output working transcript to `--output` file or stdout.
14. Build process report (`phase` currently set to `phase7-runner`).
15. Optionally write `--report-json`; always write run-dir `report.json`.
16. Apply work-dir retention.
Important behavior details:
- Glossary is validated but not yet used for correction logic.
- No module execution occurs despite `--modules` config support.
- Glossary is validated but not yet used for real correction module logic.
- Default production CLI behavior remains deterministic normalization/chunking output because no real module implementations are registered yet.
- No LLM calls occur.
- Success path is generally quiet on stderr.
- Source IDs are preserved into a canonical transcript before normalization; normalization then reassigns output IDs sequentially from `1`.
@@ -187,7 +192,7 @@ Current behavior details:
`internal/framework/contracts` provides interfaces and run-spec metadata scaffolding, including deterministic repeated module instance naming (`ResolveModuleRunSpecs`).
These are framework primitives only; they are not yet wired into CLI runtime module execution.
These primitives are wired into the production runner and report model. Real module implementations are still pending.
## Reports and diagnostics (implemented)
Current per-run artifacts include:
@@ -214,6 +219,10 @@ Current process reports include diagnostics metadata references for:
- redacted effective-config artifact path;
- error-log artifact path on failure.
Current process reports also include:
- module-level results (when runner modules execute), including applied/skipped proposal changes;
- run-level module summary totals and failed module instance metadata.
Retention modes implemented in `ApplyRetention`:
- `always`: keep all run directories.
- `never`: keep successful run directories.
@@ -221,7 +230,7 @@ Retention modes implemented in `ApplyRetention`:
- failed runs are always retained.
Current runtime note:
- module execution is not implemented yet, so successful runs generally have no skipped corrections and `auto` typically removes clean successful run directories.
- real module execution is not implemented yet, so normal successful runs generally have no skipped corrections and `auto` typically removes clean successful run directories.
Intentionally deferred to module/LLM phases:
- module prompt/response diagnostics artifacts are not produced yet because module execution and LLM calls are not in the runtime path.
@@ -236,8 +245,10 @@ Implemented tests currently cover:
- deterministic chunking and summaries (`internal/core/chunking/*_test.go`)
- proposal preview/apply semantics (`internal/framework/proposals/*_test.go`)
- contracts/foundation composition tests (`internal/framework/contracts/*_test.go`)
- runner sequencing and failure behavior with deterministic fake modules (`internal/framework/runner/*_test.go`)
- CLI runner integration through injected fake module factories (`internal/cli/run_test.go`)
Not covered yet (because not implemented): end-to-end module runner behavior, validator runtime flow, and real LLM integration.
Not covered yet (because not implemented): validator runtime flow with approvals/rejections and real LLM integration.
## Intended final architecture (not yet implemented)
The intended end-state still matches the rewrite plan:
@@ -247,6 +258,6 @@ The intended end-state still matches the rewrite plan:
- deterministic and LLM validators
- validator cardinality enforcement in pipeline execution
- proposal application integrated per module stage
- richer run reporting with module-level applied/skipped changes
- prompt/response diagnostics for LLM/module stages
Until those phases are implemented, documentation and external descriptions should treat the current Go CLI as deterministic preprocessing/reporting infrastructure, not a full LLM transcript polisher.